# Machine Learning Methods for Spectral Efficiency Prediction in Massive MIMO Systems

arXiv: https://arxiv.org/abs/2112.14423 · HTML: https://mlsanity.com/paper/2112.14423/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 46 references that are in the map.
- First posted on arXiv 29 Dec 2021.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Deep Learning Power Allocation in Massive MIMO](https://mlsanity.com/paper/1812.03640/) (2018)
- [Bayesian Sparsification of Recurrent Neural Networks](https://mlsanity.com/paper/1708.00077/) (2017)
- [Massive MIMO Adaptive Modulation and Coding Using Online Deep Learning Algorithm](https://mlsanity.com/paper/2105.12827/) (2021)
- [Uplink power control in cell-free massive MIMO via deep learning](https://mlsanity.com/paper/1908.11121/) (2019)
- [Regularized Zero-Forcing for Multiantenna Broadcast Channels with User Selection](https://mlsanity.com/paper/2003.09923/) (2020)
- [Adaptive Regularized Zero-Forcing Beamforming in Massive MIMO with Multi-Antenna Users](https://mlsanity.com/paper/2107.00853/) (2021)
- [Model-Aided Wireless Artificial Intelligence: Embedding Expert Knowledge in Deep Neural Networks Towards Wireless Systems Optimization](https://mlsanity.com/paper/1808.01672/) (2018)

## Abstract (arXiv)

Channel decoding, channel detection, channel assessment, and resource management for wireless multiple-input multiple-output (MIMO) systems are all examples of problems where machine learning (ML) can be successfully applied. In this paper, we study several ML approaches to solve the problem of estimating the spectral efficiency (SE) value for a certain precoding scheme, preferably in the shortest possible time. The best results in terms of mean average percentage error (MAPE) are obtained with gradient boosting over sorted features, while linear models demonstrate worse prediction quality. Neural networks perform similarly to gradient boosting, but they are more resource- and time-consuming because of hyperparameter tuning and frequent retraining. We investigate the practical applicability of the proposed algorithms in a wide range of scenarios generated by the Quadriga simulator. In almost all scenarios, the MAPE achieved using gradient boosting and neural networks is less than 10%.